nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/nf-core/mspepid/main/nextflow_schema.json",
    "title": "nf-core/mspepid pipeline parameters",
    "description": "A pipeline for the identification of peptides in mass spectrometry data.",
    "type": "object",
    "$defs": {
        "input_output_options": {
            "title": "Input/output options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define where the pipeline should find input data and save output data.",
            "required": ["input", "outdir"],
            "properties": {
                "input": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "schema": "assets/schema_input.json",
                    "mimetype": "text/csv",
                    "pattern": "^\\S+\\.csv$",
                    "description": "Path to comma-separated file containing information about the samples in the experiment.",
                    "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/mspepid/usage#samplesheet-input).",
                    "fa_icon": "fas fa-file-csv"
                },
                "outdir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
                    "fa_icon": "fas fa-folder-open"
                },
                "email": {
                    "type": "string",
                    "description": "Email address for completion summary.",
                    "fa_icon": "fas fa-envelope",
                    "help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
                }
            }
        },
        "database_options": {
            "title": "Database Options",
            "type": "object",
            "fa_icon": "fas fa-database",
            "description": "Database settings, to specify the FASTA, create decoys and entrapments",
            "properties": {
                "fasta": {
                    "type": "string",
                    "fa_icon": "fas fa-file",
                    "pattern": "^\\S+\\.(fasta|fa|fas|faa)(.gz)?$",
                    "description": "Global input FASTA protein database (mutually exclusive with per-run 'fasta' column in the samplesheet)",
                    "help_text": "Path to a single protein database file applied to all MS runs. Cannot be used together with the 'fasta' column in the samplesheet. Whether the file already contains decoys is controlled by --skip_decoy_generation."
                },
                "entrapment_fold": {
                    "type": "integer",
                    "default": 0,
                    "description": "This parameter specifies for an entrapment search the fold of entrapment proteins per target protein. No database will be created if 0."
                },
                "skip_decoy_generation": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Add this parameter when you want to skip the generation of the decoy database.",
                    "help_text": "If you want to use your own decoys, you can specify a dataset that includes decoy sequences."
                }
            }
        },
        "general_search_parameters": {
            "title": "General search parameters",
            "type": "object",
            "description": "Search parameters that are common to all search engines.",
            "properties": {
                "precursor_tol_ppm": {
                    "type": "integer",
                    "default": 10,
                    "description": "The precursor tolerance in PPM"
                },
                "fragment_tol_da": {
                    "type": "number",
                    "default": 0.02,
                    "description": "The fragment tolerance in Dalton"
                }
            }
        },
        "sage_search_parameters": {
            "title": "Sage search parameters",
            "type": "object",
            "description": "Search parameters specific to Sage",
            "properties": {
                "sage_config_template": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to the Sage params file. If not set or null, the provided default in assets is used.",
                    "fa_icon": "fas fa-cogs"
                },
                "sage_prefilter": {
                    "type": "boolean",
                    "default": false,
                    "description": "Whether the database should be split during Sage search. This greatly reduces memory consumption when using large databases (beta feature)"
                },
                "sage_prefilter_chunk_size": {
                    "type": "integer",
                    "default": 0,
                    "description": "Number of proteins per database chunk when prefiltering is active."
                }
            }
        },
        "identification_options": {
            "title": "Select search engines to be executed",
            "type": "object",
            "description": "Enable/disable search engines.",
            "properties": {
                "run_comet": {
                    "type": "boolean",
                    "default": true,
                    "description": "Enables spectrum identification with Comet."
                },
                "run_sage": {
                    "type": "boolean",
                    "default": true,
                    "description": "Enables spectrum identification with Sage."
                },
                "comet_config_template": {
                    "type": "string",
                    "format": "file-path",
                    "description": "This is the default comet parameters file. In this file, parameters can be set, which are neither passed by common runtime (threads, fasta, ...) or by common search engine parameters. If not set or null, the provided default in assets is used.",
                    "fa_icon": "fas fa-cogs"
                }
            }
        },
        "rescoring_options": {
            "title": "Select rescoring algorithms to be executed",
            "type": "object",
            "description": "Enable/disable rescoring algorithms.",
            "properties": {
                "run_percolator": {
                    "type": "boolean",
                    "default": true,
                    "description": "Enables rescoring with Percolator. Some rescorings (MS2Rescore, Oktoberfest) depend on Percolator results, so Percolator will be run if any of these are enabled, even if this parameter is set to false."
                },
                "run_ms2rescore": {
                    "type": "boolean",
                    "default": true,
                    "description": "Enables rescoring with MS2Rescore."
                },
                "ms2rescore_model": {
                    "type": "string",
                    "default": "HCD",
                    "description": "The MS2PIP model to use for MS2Rescore. Models can be found here: https://ms2pip.readthedocs.io/en/latest/prediction-models/"
                },
                "ms2rescore_model_dir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Optional directory with pre-downloaded MS2PIP model files. If set to null, the respective model is downloaded and saved in the results directory.",
                    "fa_icon": "fas fa-folder-open"
                }
            }
        },
        "institutional_config_options": {
            "title": "Institutional config options",
            "type": "object",
            "fa_icon": "fas fa-university",
            "description": "Parameters used to describe centralised config profiles. These should not be edited.",
            "help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.",
            "properties": {
                "custom_config_version": {
                    "type": "string",
                    "description": "Git commit id for Institutional configs.",
                    "default": "master",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "custom_config_base": {
                    "type": "string",
                    "description": "Base directory for Institutional configs.",
                    "default": "https://raw.githubusercontent.com/nf-core/configs/master",
                    "hidden": true,
                    "help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.",
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_name": {
                    "type": "string",
                    "description": "Institutional config name.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_description": {
                    "type": "string",
                    "description": "Institutional config description.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_contact": {
                    "type": "string",
                    "description": "Institutional config contact information.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_url": {
                    "type": "string",
                    "description": "Institutional config URL link.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                }
            }
        },
        "generic_options": {
            "title": "Generic options",
            "type": "object",
            "fa_icon": "fas fa-file-import",
            "description": "Less common options for the pipeline, typically set in a config file.",
            "help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.",
            "properties": {
                "version": {
                    "type": "boolean",
                    "description": "Display version and exit.",
                    "fa_icon": "fas fa-question-circle",
                    "hidden": true
                },
                "publish_dir_mode": {
                    "type": "string",
                    "default": "copy",
                    "description": "Method used to save pipeline results to output directory.",
                    "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                    "fa_icon": "fas fa-copy",
                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
                    "hidden": true
                },
                "email_on_fail": {
                    "type": "string",
                    "description": "Email address for completion summary, only when pipeline fails.",
                    "fa_icon": "fas fa-exclamation-triangle",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
                    "help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
                    "hidden": true
                },
                "plaintext_email": {
                    "type": "boolean",
                    "description": "Send plain-text email instead of HTML.",
                    "fa_icon": "fas fa-remove-format",
                    "hidden": true
                },
                "monochrome_logs": {
                    "type": "boolean",
                    "description": "Do not use coloured log outputs.",
                    "fa_icon": "fas fa-palette",
                    "hidden": true
                },
                "validate_params": {
                    "type": "boolean",
                    "description": "Boolean whether to validate parameters against the schema at runtime",
                    "default": true,
                    "fa_icon": "fas fa-check-square",
                    "hidden": true
                },
                "pipelines_testdata_base_path": {
                    "type": "string",
                    "fa_icon": "far fa-check-circle",
                    "description": "Base URL or local path to location of pipeline test dataset files",
                    "default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
                    "hidden": true
                },
                "trace_report_suffix": {
                    "type": "string",
                    "fa_icon": "far calendar",
                    "description": "Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.",
                    "hidden": true
                },
                "help": {
                    "type": ["boolean", "string"],
                    "description": "Display the help message."
                },
                "help_full": {
                    "type": "boolean",
                    "description": "Display the full detailed help message."
                },
                "show_hidden": {
                    "type": "boolean",
                    "description": "Display hidden parameters in the help message (only works when --help or --help_full are provided)."
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/$defs/input_output_options"
        },
        {
            "$ref": "#/$defs/database_options"
        },
        {
            "$ref": "#/$defs/general_search_parameters"
        },
        {
            "$ref": "#/$defs/identification_options"
        },
        {
            "$ref": "#/$defs/sage_search_parameters"
        },
        {
            "$ref": "#/$defs/rescoring_options"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ]
}